LLM EXPLORER 58,873 MODELS INDEXED

MiroThinker 1.7 Mini Mlx 4Bit by mlx-community

By mlx-community · 37 downloads
HF Repo ↗ Copy URL

MiroThinker 1.7 Mini Mlx 4Bit is an open-source language model by mlx-community. Features: 30.5b LLM, VRAM: 17.2GB, Context: 256K, License: apache-2.0, Quantized, LLM Explorer Score: 0.23.

  4-bit   4bit   Agent Base model:miromind-ai/mirothi... Base model:quantized:miromind-...   Conversational   Deep-research   En   Endpoints compatible   Miromind   Mlx   Mlx-my-repo   Open-source   Quantized   Qwen3 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/MiroThinker-1.7-mini-mlx-4Bit 

MiroThinker 1.7 Mini Mlx 4Bit Parameters and Internals

LLM NameMiroThinker 1.7 Mini Mlx 4Bit
Repository 🤗https://huggingface.co/mlx-community/MiroThinker-1.7-mini-mlx-4Bit 
Base Model(s)  miromind-ai/MiroThinker-1.7-mini   miromind-ai/MiroThinker-1.7-mini
Model Size30.5b
Required VRAM17.2 GB
Updated2026-07-20
Maintainermlx-community
Model Typeqwen3_moe
Model Files  5.3 GB: 1-of-4   5.4 GB: 2-of-4   5.3 GB: 3-of-4   1.2 GB: 4-of-4
Supported Languagesen
Quantization Type4bit
Model ArchitectureQwen3MoeForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version4.51.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to MiroThinker 1.7 Mini Mlx 4Bit

Best Alternatives
Context / RAM
Downloads
Likes
SU 01256K / 61.1 GB19928
SimpleChat 30BA3B V2195K / 61.1 GB155
Rubicon Preview40K / 61.1 GB3925
SimpleChat 30BA3B V139K / 61.1 GB71
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/MiroThinker-1.7-mini-mlx-4Bit.